Hitachi Construction Machinery : Begins R&D of Physical AI That Learns Hydraulic Excavator Operator Skills

Tokyo, September 9, 2026 - Hitachi Construction Machinery Co., Ltd. (Head Office: Taito-ku, Tokyo, Japan; President and Executive Officer: Masafumi Senzaki; "Hitachi Construction Machinery") will begin research and development of Physical AI that learns hydraulic excavator operator skills ("the project") in October 2026. The project will develop Physical AI trained on operator lever operations using information such as camera images and work instructions to determine and execute appropriate operations based on site conditions. In the future, the project aims to achieve autonomous operation in debris removal work at disaster sites as well as excavation and loading work at construction and mining sites.

The project has been selected for GENIAC (Generative AI Accelerator Challenge), a national project implemented by Japan's Ministry of Economy, Trade and Industry (METI) and the New Energy and Industrial Technology Development Organization (NEDO) with the aim of strengthening Japan's generative AI development capabilities and promoting the social implementation of generative AI. Hitachi Construction Machinery will advance this project in collaboration with Jizai, Inc. (Head Office: Bunkyo-ku, Tokyo; Representative Director and CEO: Yuki Ishikawa) and the Nara Institute of Science and Technology (NAIST).

In the construction and mining industries, there is a growing demand to address labor shortages while improving safety and productivity in harsh work environments. Moreover, the importance of rapidly responding to increasingly severe natural disasters and ensuring a stable supply of mineral resources has also risen in recent years.

Hydraulic excavators must operate according to varying construction site conditions such as the shape and position of objects, surrounding environment, weather, etc. Therefore, achieving autonomous operation requires technology that is capable of determining appropriate operations while recognizing the surrounding conditions. Hitachi Construction Machinery has been conducting research and development related to autonomous operation. The project aims to realize construction machinery that autonomously performs tasks according to the site environment by developing a new AI trained on the operational data of human operators.

The project will focus on the development of Physical AI trained on the operational data of human operators to make appropriate decisions and perform appropriate operations according to construction site conditions and work instructions.

Physical AI is a technology capable of recognizing real-world conditions and autonomously making decisions and taking actions, which is increasingly applied to industrial robots, humanoid robots, etc. Hitachi Construction Machinery regards Physical AI as a technology for realizing safe and efficient construction by enabling construction and mining machinery to autonomously execute a series of processes consisting of "understanding the surrounding environment (perception)," "work plan optimization (decision)," and "operation execution (action)." Physical AI is not merely mechanical automation, as the AI understands the machinery and surrounding environment to autonomously carry out construction tasks.

Hitachi Construction Machinery will collect extensive operator work footage and operation logs to train the Physical AI under development. The project aims to develop Physical AI that achieves highly accurate and autonomous decision-making and construction even on actual construction sites by training the AI on the operational data acquired under a diverse range of conditions including regular operations as well as recovery processes from operational errors, weather, the surrounding environment, machinery conditions, object positioning, etc.

The project will be carried out through industry-academia collaboration. The primary roles of each participating institution are as follows.

Through the project, Hitachi Construction Machinery aims to establish autonomous operation technology using AI trained on the operational data of human operators. In the future, Hitachi Construction Machinery will help solve social issues such as labor shortages and improvements in safety and productivity by deploying Physical AI in a broad range of fields including disaster response, material handling, forestry, mining, demolition, and civil engineering.

• September 9, 2026 NEDO announcement
  Decision on the Project Implementation Structure for the "Post-5G Information and Communication System Infrastructure Enhancement R&D Project / Research and Development of Robot Foundation Models (GENIAC) (Subsidy)," including multipurpose robots (Japanese)
• September 9, 2026 Jizai, Inc. press release
  Jizai Joins Hitachi Construction Machinery's GENIAC-Selected R&D Program on Physical AI That Learns Hydraulic Excavator Operator Skills

Hitachi Construction Machinery Co., Ltd. (TSE: 6305), headquartered in Tokyo, Japan, is a construction machinery manufacturer that globally deploys development, manufacturing, sales, and service businesses for its hydraulic excavators, wheel loaders, compaction equipment, and mining machinery, etc. In addition to its new machinery business, Hitachi Construction Machinery is expanding its "value chain businesses" of parts and services, remanufacturing (parts and machines), rentals, and used equipment as it continues to grow together with customers as a solutions provider that offers innovative solutions to customers. With roughly 25,000 employees around the world, the consolidated sales revenue for Hitachi Construction Machinery was 1,405.5 billion yen for fiscal year 2025 (ended March 2026) with an overseas sales revenue ratio of 84%. For more details, please see the company's website.

The company plans to change its trade name to "LANDCROS Corporation" and its corporate brand to "LANDCROS" on April 1, 2027.

Information contained in this news release is current as of the date of the press announcement, but may be subject to change without prior notice.